abuzreq / ComfyUI-Model-BendingLinks
A ComfyUI custom node implementing model bending which helps in pushing your model towards more diverse outputs.
☆15Updated this week
Alternatives and similar repositories for ComfyUI-Model-Bending
Users that are interested in ComfyUI-Model-Bending are comparing it to the libraries listed below
Sorting:
- Latent Terrain - Dissecting the Latent Space of Neural Audio Autoencoders☆31Updated 3 weeks ago
- Neural network bending framework for creativity in Pytorch☆33Updated 10 months ago
- fork of the RAVE model: a Realtime Audio Variational autoEncoder☆44Updated 4 months ago
- VST/AU Plugin for Auditioning RAVE Models in Real-time☆84Updated 3 years ago
- vintage neural synthesis with spectral auto-encoders☆67Updated 2 months ago
- Rhythm generator using Variational Autoencoder(VAE)☆36Updated 3 years ago
- The hybrid architecture is based on the idea that we could simply apply a GAN method (GANSpace) to another GAN model (GANSynth).☆25Updated 4 years ago
- Continuous descriptor-based control for deep audio synthesis☆21Updated 2 years ago
- AFTER : Audio Features Transfer and Exploration in Real-time☆88Updated last month
- Generate new latent codes for RAVE with Denoising Diffusion models.☆180Updated 10 months ago
- Notochord is a real-time neural network model for MIDI performances.☆30Updated last month
- A Max for Live device based on nn~ for real-time latent interaction and bending in Ableton.☆17Updated 3 months ago
- ☆18Updated last month
- ☆16Updated 3 years ago
- StyleGAN2 + MelGAN Audio Loop Generation☆104Updated last year
- Max/MSP, PureData and Unity plugins to load Pytorch models☆26Updated last year
- Low-latency timbre transfer models for instrumental interaction.☆77Updated last week
- ☆47Updated 4 years ago
- ICMC 2020 "Neural Granular Sound Synthesis"☆37Updated 3 years ago
- Performative Latents for Adaptive Unsupervised DDSP (PLAUD)☆13Updated last month
- ☆47Updated last week
- Create presets for Scyclone: a Real-time Neural Timbre Transfer Plug-in☆35Updated last year
- Official repo of ISMIR-21 publication, “A Benchmarking Initiative for Audio-domain Music Generation using the FreeSound Loop Dataset”.☆82Updated 3 years ago
- Abstractions for Latent Jamming with nn~ compatible neural audio models written in Pure Data☆14Updated 3 weeks ago
- Creative Adversarial Network for generating Dance Music Rhythm Patterns☆33Updated 2 years ago
- Style-based Neural Drum Synthesis with GAN inversion☆32Updated 3 years ago
- Interactive Learning of Microtiming in an Expressive Drum Machine☆13Updated 2 years ago
- MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms☆11Updated 3 years ago
- Flexible LoRA Implementation to use with stable-audio-tools☆76Updated last year
- ☆14Updated last month